perf/core: Add aux_pause, aux_resume, aux_start_paused

Hardware traces, such as instruction traces, can produce a vast amount of
trace data, so being able to reduce tracing to more specific circumstances
can be useful.

The ability to pause or resume tracing when another event happens, can do
that.

Add ability for an event to "pause" or "resume" AUX area tracing.

Add aux_pause bit to perf_event_attr to indicate that, if the event
happens, the associated AUX area tracing should be paused. Ditto
aux_resume. Do not allow aux_pause and aux_resume to be set together.

Add aux_start_paused bit to perf_event_attr to indicate to an AUX area
event that it should start in a "paused" state.

Add aux_paused to struct hw_perf_event for AUX area events to keep track of
the "paused" state. aux_paused is initialized to aux_start_paused.

Add PERF_EF_PAUSE and PERF_EF_RESUME modes for ->stop() and ->start()
callbacks. Call as needed, during __perf_event_output(). Add
aux_in_pause_resume to struct perf_buffer to prevent races with the NMI
handler. Pause/resume in NMI context will miss out if it coincides with
another pause/resume.

To use aux_pause or aux_resume, an event must be in a group with the AUX
area event as the group leader.

Example (requires Intel PT and tools patches also):

 $ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname
 Linux
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.043 MB perf.data ]
 $ perf script --call-trace
 uname   30805 [000] 24001.058782799: name: 0x7ffc9c1865b0
 uname   30805 [000] 24001.058784424:  psb offs: 0
 uname   30805 [000] 24001.058784424:  cbr: 39 freq: 3904 MHz (139%)
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])        debug_smp_processor_id
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])        __x64_sys_newuname
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])            down_read
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])                __cond_resched
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])                preempt_count_add
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])                    in_lock_functions
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])                preempt_count_sub
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])            up_read
 uname   30805 [000] 24001.058784629: ([kernel.kallsyms])                preempt_count_add
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])                    in_lock_functions
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])                preempt_count_sub
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])            _copy_to_user
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])        syscall_exit_to_user_mode
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])            syscall_exit_work
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])                perf_syscall_exit
 uname   30805 [000] 24001.058784838: ([kernel.kallsyms])                    debug_smp_processor_id
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                    perf_trace_buf_alloc
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                        perf_swevent_get_recursion_context
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                            debug_smp_processor_id
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                        debug_smp_processor_id
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                    perf_tp_event
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                        perf_trace_buf_update
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                            tracing_gen_ctx_irq_test
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                        perf_swevent_event
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                            __perf_event_account_interrupt
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                                __this_cpu_preempt_check
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                            perf_event_output_forward
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                                perf_event_aux_pause
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                                    ring_buffer_get
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                                        __rcu_read_lock
 uname   30805 [000] 24001.058785046: ([kernel.kallsyms])                                        __rcu_read_unlock
 uname   30805 [000] 24001.058785254: ([kernel.kallsyms])                                    pt_event_stop
 uname   30805 [000] 24001.058785254: ([kernel.kallsyms])                                        debug_smp_processor_id
 uname   30805 [000] 24001.058785254: ([kernel.kallsyms])                                        debug_smp_processor_id
 uname   30805 [000] 24001.058785254: ([kernel.kallsyms])                                        native_write_msr
 uname   30805 [000] 24001.058785463: ([kernel.kallsyms])                                        native_write_msr
 uname   30805 [000] 24001.058785639: 0x0

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: James Clark <james.clark@arm.com>
Link: https://lkml.kernel.org/r/20241022155920.17511-3-adrian.hunter@intel.com

1 files changed, 71 insertions, 4 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index e3589c4287cb..0e9cfe6f3535 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2146,7 +2146,7 @@ static void perf_put_aux_event(struct perf_event *event)
 
 static bool perf_need_aux_event(struct perf_event *event)
 {
-	return !!event->attr.aux_output || !!event->attr.aux_sample_size;
+	return event->attr.aux_output || has_aux_action(event);
 }
 
 static int perf_get_aux_event(struct perf_event *event,
@@ -2171,6 +2171,10 @@ static int perf_get_aux_event(struct perf_event *event,
 	    !perf_aux_output_match(event, group_leader))
 		return 0;
 
+	if ((event->attr.aux_pause || event->attr.aux_resume) &&
+	    !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+		return 0;
+
 	if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
 		return 0;
 
@@ -8016,6 +8020,49 @@ void perf_prepare_header(struct perf_event_header *header,
 	WARN_ON_ONCE(header->size & 7);
 }
 
+static void __perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+	if (pause) {
+		if (!event->hw.aux_paused) {
+			event->hw.aux_paused = 1;
+			event->pmu->stop(event, PERF_EF_PAUSE);
+		}
+	} else {
+		if (event->hw.aux_paused) {
+			event->hw.aux_paused = 0;
+			event->pmu->start(event, PERF_EF_RESUME);
+		}
+	}
+}
+
+static void perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+	struct perf_buffer *rb;
+
+	if (WARN_ON_ONCE(!event))
+		return;
+
+	rb = ring_buffer_get(event);
+	if (!rb)
+		return;
+
+	scoped_guard (irqsave) {
+		/*
+		 * Guard against self-recursion here. Another event could trip
+		 * this same from NMI context.
+		 */
+		if (READ_ONCE(rb->aux_in_pause_resume))
+			break;
+
+		WRITE_ONCE(rb->aux_in_pause_resume, 1);
+		barrier();
+		__perf_event_aux_pause(event, pause);
+		barrier();
+		WRITE_ONCE(rb->aux_in_pause_resume, 0);
+	}
+	ring_buffer_put(rb);
+}
+
 static __always_inline int
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
@@ -9818,9 +9865,12 @@ static int __perf_event_overflow(struct perf_event *event,
 
 	ret = __perf_event_account_interrupt(event, throttle);
 
+	if (event->attr.aux_pause)
+		perf_event_aux_pause(event->aux_event, true);
+
 	if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
 	    !bpf_overflow_handler(event, data, regs))
-		return ret;
+		goto out;
 
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
@@ -9882,6 +9932,9 @@ static int __perf_event_overflow(struct perf_event *event,
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending_irq);
 	}
+out:
+	if (event->attr.aux_resume)
+		perf_event_aux_pause(event->aux_event, false);
 
 	return ret;
 }
@@ -12273,11 +12326,25 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	}
 
 	if (event->attr.aux_output &&
-	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+	    (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
+	     event->attr.aux_pause || event->attr.aux_resume)) {
 		err = -EOPNOTSUPP;
 		goto err_pmu;
 	}
 
+	if (event->attr.aux_pause && event->attr.aux_resume) {
+		err = -EINVAL;
+		goto err_pmu;
+	}
+
+	if (event->attr.aux_start_paused) {
+		if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
+			err = -EOPNOTSUPP;
+			goto err_pmu;
+		}
+		event->hw.aux_paused = 1;
+	}
+
 	if (cgroup_fd != -1) {
 		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
 		if (err)
@@ -13073,7 +13140,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	 * Grouping is not supported for kernel events, neither is 'AUX',
 	 * make sure the caller's intentions are adjusted.
 	 */
-	if (attr->aux_output)
+	if (attr->aux_output || attr->aux_action)
 		return ERR_PTR(-EINVAL);
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,